Huibin Lin — accepted AI-conference papers

2025

Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded Boundary

Yuena Lin, Yiyuan Wang, Gengyu Lyu, Yongjian Deng, Haichun Cai, Huibin Lin +2

ICLR 2025poster

Multi-view classification aims at unifying the data from multiple views to complementarily enhance the classification performance. Unfortunately, two major problems in multi-view data are damaging model performance. The first is feature heterogeneity, which makes it hard to fuse features from differ…

Cited by 0 Source ↗PDF ↗Scholar ↗

2019

Furcax: End-to-end Monaural Speech Separation Based on Deep Gated (De)convolutional Neural Networks with Adversarial Example Training

Ziqiang Shi, Huibin Lin, Liu Liu, Rujie Liu, Shoji Hayakawa, Jiqing Han

ICASSP 2019accepted

Deep gated convolutional networks have been proved to be very effective in single channel speech separation. However current state-of-the-art framework often considers training the gated convolutional networks in time-frequency (TF) domain. Such an approach will result in limited perceptual score, s…

Cited by 0 Source ↗Scholar ↗